Up2Europe est un accélérateur d’idées pour des projets de coopération.
La plateforme Ma Région Sud fait partie de l'écosystème de Up2Europe qui permet de booster la coopération à un niveau supérieur!
Besoin d'aide ? La Région Sud vous accompagne
Laissez-vous guider par notre équipe d'experts ! Saisissez votre mail et nous reviendrons vers vous rapidement
Convex Optimization Methods for Computer Vision an.. (CONVEXVISION)
Convex Optimization Methods for Computer Vision and Image Analysis
(CONVEXVISION)
Date du début: 1 sept. 2010,
Date de fin: 31 août 2015
PROJET
TERMINÉ
Optimization methods have become an established paradigm to address most Computer Vision challenges including thereconstruction of three-dimensional objects from multiple images, or the tracking of a deformable shape over time. Yet, it hasbeen largely overlooked that optimization approaches are practically useless if they do not come with efficient algorithms tocompute minimizers of respective energies. Most existing formulations give rise to non-convex energies. As a consequence,solutions highly depend on the choice of minimization scheme and implementational (initialization, time step sizes, etc.), withlittle or no guarantees regarding the quality of computed solutions and their robustness to perturbations of the input data.In the proposed research project, we plan to develop optimization methods for Computer Vision which allow to efficientlycompute globally optimal solutions. Preliminary results indicate that this will drastically leverage the power of optimizationmethods and their applicability in a substantially broader context. Specifically we will focus on three lines of research: 1) Wewill develop convex formulations for a variety of challenges. While convex formulations are currently being developed forlow-level problems such as image segmentation, our main effort will focus on carrying convex optimization to higher levelproblems of image understanding and scene interpretation. 2) We will investigate alternative strategies of global optimizationby means of discrete graph theoretic methods. We will characterize advantages and drawbacks of continuous and discretemethods and thereby develop novel algorithms combining the advantages of both approaches. 3) We will go beyond convexformulations, developing relaxation schemes that compute near-optimal solutions for problems that cannot be expressed byconvex functionals.
Accédez au prémier réseau pour la cooperation européenne
Se connecter
Bonjour, vous êtes sur la plateforme Région Sud Provence-Alpes-Côte d’Azur dédiée aux programmes thématiques et de coopération territoriale. Une équipe d’experts vous accompagne dans vos recherches de financements.
Contactez-nous !
Contactez la Région Sud Provence-Alpes-Côte d'Azur
Vous pouvez nous écrire en Anglais, Français et Italien